In EDS ansehen

Medication adherence among Jordanian adults with chronic conditions: a combined analysis using regression and machine learning.

Gespeichert in:
Bibliographische Detailangaben
Titel: Medication adherence among Jordanian adults with chronic conditions: a combined analysis using regression and machine learning.
Autoren: Al-Qerem W; Department of Pharmacy, Faculty of Pharmacy, Al-Zaytoonah University of Jordan, Amman, Jordan., Jarab A; Department of Clinical Pharmacy, Faculty of Pharmacy, Jordan University of Science and Technology, Irbid, Jordan., Eberhardt J; Department of Psychology, School of Social Sciences, Humanities and Law, Teesside University, Middlesbrough, UK., Abdo S; Department of Pharmacy, Faculty of Pharmacy, Al-Zaytoonah University of Jordan, Amman, Jordan., Al-Sa'di L; Department of Pharmacy, Faculty of Pharmacy, Al-Zaytoonah University of Jordan, Amman, Jordan., Al-Shehadeh R; Department of Pharmacy, Faculty of Pharmacy, Al-Zaytoonah University of Jordan, Amman, Jordan., Khasim D; Department of Pharmacy, Faculty of Pharmacy, Al-Zaytoonah University of Jordan, Amman, Jordan., Zumot R; Department of Pharmacy, Faculty of Pharmacy, Al-Zaytoonah University of Jordan, Amman, Jordan., Khalil S; Department of Pharmacy, Faculty of Pharmacy, Al-Zaytoonah University of Jordan, Amman, Jordan.
Quelle: Annals of medicine [Ann Med] 2025 Dec; Vol. 57 (1), pp. 2548979. Date of Electronic Publication: 2025 Aug 20.
Publikationsart: Journal Article
Sprache: English
Info zur Zeitschrift: Publisher: Informa Healthcare Country of Publication: England NLM ID: 8906388 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1365-2060 (Electronic) Linking ISSN: 07853890 NLM ISO Abbreviation: Ann Med Subsets: MEDLINE
Imprint Name(s): Publication: London : Informa Healthcare
Original Publication: Helsinki : Finnish Medical Society Duodecim, 1989-
MeSH-Schlagworte: Machine Learning* , Health Literacy*/statistics & numerical data , Medication Adherence*/psychology, Humans ; Female ; Male ; Cross-Sectional Studies ; Middle Aged ; Jordan/epidemiology ; Chronic Disease/drug therapy ; Adult ; Aged ; Surveys and Questionnaires ; Regression Analysis
Abstract: Background: Managing chronic illness effectively depends not only on treatment availability but also on patients' ability to adhere to prescribed medications.
Objectives: This study examined the factors influencing medication adherence among Jordanian adults with long-term conditions, using both traditional regression and machine learning methods.
Method: In this cross-sectional study, patients with chronic conditions completed an online survey that assessed demographic, clinical and behavioural variables, including Health Literacy Questionnaire (HLQ-12) and adherence (MARS-5). Quantile regression and machine learning models were applied.
Results: A total of 981 patients (63.1% females) were enrolled in the study. Quantile regression showed that higher health literacy, a diagnosis of diabetes or cardiovascular disease, and fewer prescribed medications were positively associated with adherence. In contrast, being married or having public, military or no insurance was linked to lower adherence scores. The Random Forest model achieved the highest predictive accuracy ( R2 = 0.38), and SHAP analysis identified health literacy, disease duration and age as the most influential features.
Conclusions: These findings highlight the need for targeted interventions that address both individual understanding and structural challenges, such as insurance type and treatment complexity. Improving health literacy, simplifying medication regimens, and ensuring equitable healthcare access may help support better adherence in this population. The use of explainable machine learning, alongside conventional statistical approaches, offers new opportunities to improve the understanding and prediction of adherence behaviours in resource-constrained settings.
References: Prev Chronic Dis. 2021 Apr 08;18:E33. (PMID: 33830913)
Br J Clin Pharmacol. 2014 Mar;77(3):427-45. (PMID: 23803249)
Health Aff (Millwood). 2003 Jul-Aug;22(4):220-9. (PMID: 12889771)
PLoS One. 2013 Dec 02;8(12):e80633. (PMID: 24312488)
J Gen Intern Med. 2018 Feb;33(2):200-206. (PMID: 29204971)
Br J Clin Pharmacol. 2020 Jul;86(7):1281-1288. (PMID: 31823381)
J Acquir Immune Defic Syndr. 2006 Dec 1;43 Suppl 1:S54-68. (PMID: 17133205)
J Am Geriatr Soc. 2017 Apr;65(4):747-753. (PMID: 27991653)
Diabetes Care. 2011 Feb;34(2):338-40. (PMID: 21270191)
PLoS One. 2021 Aug 23;16(8):e0256666. (PMID: 34424940)
Health Aff (Millwood). 2010 Dec;29(12):2323-34. (PMID: 21088012)
JAMA Intern Med. 2015 May;175(5):827-34. (PMID: 25798731)
Public Health. 2005 Dec;119(12):1130-2. (PMID: 16084543)
Eur J Clin Pharmacol. 2022 May;78(5):869-877. (PMID: 35156130)
PLoS One. 2022 Apr 12;17(4):e0266606. (PMID: 35413086)
JCO Clin Cancer Inform. 2022 Sep;6:e2200005. (PMID: 36194843)
J Clin Pharm Ther. 2001 Oct;26(5):331-42. (PMID: 11679023)
East Mediterr Health J. 2021 Dec 28;27(12):1153-1161. (PMID: 35137383)
Health Promot Int. 2023 Jun 1;38(3):. (PMID: 37133881)
Ann Pharmacother. 2014 May;48(5):589-95. (PMID: 24523393)
PLoS One. 2024 Aug 13;19(8):e0304829. (PMID: 39137231)
Lancet. 2024 May 18;403(10440):2204-2256. (PMID: 38762325)
Heart Lung. 2012 Mar-Apr;41(2):107-14. (PMID: 22054720)
Diabetes Care. 2004 Feb;27(2):384-91. (PMID: 14747218)
J Behav Med. 2016 Dec;39(6):935-946. (PMID: 27515801)
PLoS One. 2021 Jul 09;16(7):e0254351. (PMID: 34242343)
Women Health. 2014;54(6):502-12. (PMID: 24911261)
J Behav Med. 2008 Jun;31(3):213-24. (PMID: 18202907)
Health Lit Res Pract. 2020 Oct 8;4(4):e190-e199. (PMID: 33034661)
Health Promot Int. 2021 Dec 13;36(Supplement_1):i13-i23. (PMID: 34897445)
East Mediterr Health J. 2012 Dec;18(12):1239-46. (PMID: 23301399)
Int J Environ Res Public Health. 2022 Oct 29;19(21):. (PMID: 36361025)
Contributed Indexing: Keywords: Jordan; Medication adherence; cardiovascular diseases; chronic diseases; health literacy; random Forest
Entry Date(s): Date Created: 20250820 Date Completed: 20250820 Latest Revision: 20250823
Update Code: 20250903
PubMed Central ID: PMC12369517
DOI: 10.1080/07853890.2025.2548979
PMID: 40833816
Datenbank: MEDLINE
Beschreibung
Abstract:Background: Managing chronic illness effectively depends not only on treatment availability but also on patients' ability to adhere to prescribed medications.<br />Objectives: This study examined the factors influencing medication adherence among Jordanian adults with long-term conditions, using both traditional regression and machine learning methods.<br />Method: In this cross-sectional study, patients with chronic conditions completed an online survey that assessed demographic, clinical and behavioural variables, including Health Literacy Questionnaire (HLQ-12) and adherence (MARS-5). Quantile regression and machine learning models were applied.<br />Results: A total of 981 patients (63.1% females) were enrolled in the study. Quantile regression showed that higher health literacy, a diagnosis of diabetes or cardiovascular disease, and fewer prescribed medications were positively associated with adherence. In contrast, being married or having public, military or no insurance was linked to lower adherence scores. The Random Forest model achieved the highest predictive accuracy ( R<sup>2</sup> = 0.38), and SHAP analysis identified health literacy, disease duration and age as the most influential features.<br />Conclusions: These findings highlight the need for targeted interventions that address both individual understanding and structural challenges, such as insurance type and treatment complexity. Improving health literacy, simplifying medication regimens, and ensuring equitable healthcare access may help support better adherence in this population. The use of explainable machine learning, alongside conventional statistical approaches, offers new opportunities to improve the understanding and prediction of adherence behaviours in resource-constrained settings.
ISSN:1365-2060
DOI:10.1080/07853890.2025.2548979